Rename app.py(bad) to app.py

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+from asr import transcribe_audio  # Your ASR function
+from lid import detect_language  # Your Language Identification function
+from tts import text_to_speech  # Your TTS function
+from transformers import pipeline
+
+# Load the text generation model (adjust this based on your model type)
+text_generator = pipeline("text-generation", model="Futuresony/12_10_2024.gguf")
+
+# Function to process input
+def process_input(input_text=None, audio=None):
+    if audio:  # If audio is provided, convert it to text
+        input_text = transcribe_audio(audio)
+
+    if not input_text:
+        return "No input provided", None
+    
+    # Detect language
+    lang = detect_language(input_text)
+    
+    # Generate text using the model
+    output_text = text_generator(input_text, max_length=100, do_sample=True)[0]['generated_text']
+
+    # Convert output text to speech
+    output_audio = text_to_speech(output_text, lang)
+
+    return output_text, output_audio
+
+# Create Gradio interface
+interface = gr.Interface(
+    fn=process_input,
+    inputs=[
+        gr.Textbox(label="Enter Text", placeholder="Type here..."),
+        gr.Audio(source="microphone", type="filepath", label="Record Audio")
+    ],
+    outputs=[
+        gr.Textbox(label="Generated Text"),
+        gr.Audio(label="Generated Speech")
+    ],
+    title="Speech-to-Text AI Chat",
+    description="Input text or record audio, and the AI will respond with generated text and speech."
+)
+
+# Run the demo
+interface.launch()

app.py(bad)

@@ -1,50 +0,0 @@
-import gradio as gr
-import subprocess
-import os
-from huggingface_hub import InferenceClient
-
-# Initialize Chatbot Model (Futuresony.gguf)
-chat_client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")  # Change if needed
-
-def asr_chat_tts(audio):
-    """
-    1. Convert Speech to Text using asr.py
-    2. Process text through Chat Model (Futuresony.gguf)
-    3. Convert response to Speech using tts.py
-    """
-    # Step 1: Run ASR (Speech-to-Text)
-    asr_output = subprocess.run(["python3", "asr.py", audio], capture_output=True, text=True)
-    transcription = asr_output.stdout.strip()
-
-    # Step 2: Process text through the chat model
-    messages = [{"role": "system", "content": "You are a helpful AI assistant."}]
-    messages.append({"role": "user", "content": transcription})
-
-    response = ""
-    for msg in chat_client.chat_completion(messages, max_tokens=512, stream=True):
-        token = msg.choices[0].delta.content
-        response += token
-
-    # Step 3: Run TTS (Text-to-Speech)
-    tts_output_file = "generated_speech.wav"
-    subprocess.run(["python3", "tts.py", response, tts_output_file])
-
-    return transcription, response, tts_output_file
-
-# Gradio Interface
-with gr.Blocks() as demo:
-    gr.Markdown("<h2 style='text-align: center;'>ASR → Chatbot → TTS</h2>")
-    
-    with gr.Row():
-        audio_input = gr.Audio(source="microphone", type="filepath", label="🎤 Speak Here")
-        text_transcription = gr.Textbox(label="📝 Transcription", interactive=False)
-        text_response = gr.Textbox(label="🤖 Chatbot Response", interactive=False)
-        audio_output = gr.Audio(label="🔊 Generated Speech")
-
-    submit_button = gr.Button("Process Speech 🔄")
-
-    submit_button.click(fn=asr_chat_tts, inputs=[audio_input], outputs=[text_transcription, text_response, audio_output])
-
-# Run the App
-if __name__ == "__main__":
-    demo.launch()